LLM4UACP：基于预训练 Transformer 与双域结构保持的水声信道多步预测框架
Multi-Step Underwater Acoustic Channel Prediction via Dual-Domain Structure Preservation and Pretrained Transformer
AI 导读
研究者提出 LLM4UACP 框架，通过保持信道脉冲响应与频率响应双域结构并微调冻结骨干的预训练 Transformer，一次前向即可多步预测水声信道，避免递归预测的误差累积。该方法仅用 0.11M 可训练参数，在实测 SO-06 和 SO-07 信道上 NMSE 分别达 0.0411 和 0.0399，较最新基线降低 88.53% 和 85.15%，且在有限数据与跨数据集迁移场景下保持稳健。
正文 · 原文
Abstract:Accurate future channel state information (CSI) is essential for underwater acoustic (UWA) communication because delays associated with signal propagation, feedback, scheduling, and transceiver reconfiguration can render currently available CSI outdated. However, most existing predictors estimate only the next channel state and obtain multi-step forecasts through recursive rollout, which causes prediction errors to accumulate as the multipath structure evolves. The scarcity of sea-trial measurements further limits reliable model training. To address these challenges, we propose LLM4UACP, a dual-domain, structure-preserving framework that adapts a pretrained Transformer for few-shot multi-step UWA channel prediction. LLM4UACP extracts complementary features from the channel impulse response (CIR) and channel frequency response (CFR), aligns them through Fourier-consistent fusion, and encodes the fused representation as delay-time tokens. A pretrained Transformer with a frozen backbone is adapted through Butterfly Orthogonal Fine-tuning to jointly predict multiple future CIRs in a single forward pass, thereby avoiding the error accumulation associated with recursive prediction. Experiments on the measured SO-06 and SO-07 channels show that LLM4UACP achieves normalized mean squared error (NMSE) values of 0.0411 and 0.0399, corresponding to reductions of 88.53% and 85.15%, respectively, relative to the most recent baseline. With only 0.11M trainable parameters, LLM4UACP maintains robust performance across varying prediction horizons and observation-window lengths, limited-data settings, and cross-dataset transfer scenarios.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Signal Processing (eess.SP) |
| Cite as: | arXiv:2611.14592 [cs.SD] |
| (or arXiv:2611.14592v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14592 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Deqing Wang [view email]
[v1]
Tue, 10 Nov 2026 08:38:49 UTC (3,960 KB)
来源：arXiv cs.AI · arxiv.org